> ## Documentation Index
> Fetch the complete documentation index at: https://www.truefoundry.com/llms.txt
> Use this file to discover all available pages before exploring further.
# Human in the Loop
> Pause an agent before sensitive tool calls so the user can approve or deny execution.
Some agent actions — deploying to production, restarting a service, deleting data — should not happen without explicit user consent. Human in the Loop lets the harness pause the agent before a sensitive tool call, surface the tool name and arguments to the user, and resume only after an approval decision.
This keeps the agent autonomous for safe operations while giving users a checkpoint before anything destructive or irreversible runs.
## How it works
When the agent requests a tool call that requires approval, the harness does not execute the tool. Instead, it emits `tool.approval_required`, finishes the current agent turn, and waits. The next turn — sent with `previous_response_id` and a `tool.approval` input — resumes execution with the user's decision.
```mermaid theme={"dark"}
sequenceDiagram
participant Client
participant Harness as Agent Harness
participant Tool
Client->>Harness: responses.create
Harness->>Harness: Agent calls sensitive tool
rect rgba(255, 237, 153, 0.45)
Harness-->>Client: tool.approval_required (turn ends)
Client->>Harness: tool.approval (allow / deny)
end
alt Allow
Harness->>Tool: Execute
Tool-->>Harness: Tool result
else Deny
Harness->>Harness: Use denial as tool result
end
Harness-->>Client: Agent continues
```
Approvals are derived from the tool metadata exposed by the MCP server. Tools marked as destructive or not read-only can require approval before execution.
Approvals do not replace authorization. The user still needs permission to call the underlying tool; approval only controls whether the pending tool call should proceed.
Subagents can also request approval. When a subagent's tool call requires approval, the harness finishes the current agent turn and emits `tool.approval_required`. Sending the `tool.approval` input in the next turn resumes the subagent from where it paused.
## When to use Tool Call Approvals
Use approvals for tool calls that change state, are irreversible, or affect production — for example, mutating data, modifying infrastructure, sending external communications, or triggering expensive operations.
Skip approvals for safe read-only tools — listing resources, fetching metrics, searching docs, or reading status — where confirmation adds friction without reducing risk.
## Example in the playground
When the agent calls a tool that requires approval, the playground pauses the run and shows the tool name, the request payload, and **Approve / Deny** buttons. A "1 tool needs your input" banner stays at the bottom of the chat until you decide.
After you approve, the harness executes the tool, returns the response to the agent, and the run continues to completion.
## Handling approvals from the API
For the streaming events, JSON payloads, and a full Python client that handles `tool.approval_required` and resumes the run, see [Turn events — ToolApprovalRequiredEvent](/docs/agent-platform/agent-harness/sdk/turn-events-reference#toolapprovalrequiredevent).